1. Conduid
  2. Scraping
  3. PyreCrawl
MCP server · Scraping

PyreCrawl

· github.com/SanggonBoy/PyreCrawl

One tool for AI agents to scrape, crawl, extract, map, and search the web. Self-hosted, no API keys.

Unclaimed scraping
InstallView source
37Low

Scored a month ago · breakdown

About PyreCrawl

PyreCrawl is an MCP server in the Scraping category: one tool for AI agents to scrape, crawl, extract, map, and search the web. Self-hosted, no API keys.

Install

uvx
uvx pyrecrawl
pip
pip install pyrecrawl

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (13)

batch_scrape(urls[], ...)Many URLs in ONE call — parallel, deduped, cache-aware

Parameters not published.

cache(action)Inspect/clear/enable/disable the HTTP response cache

Parameters not published.

crawl(root, max_pages=5, prefer="auto", include_paths=None, exclude_paths=None, max_depth=0)Multi-page crawl with path filters + true BFS depth

Parameters not published.

deep_research(query, limit=5, scrape_top=3)Search → evidence pack with [n] citations (no LLM synthesis — your agent does that)

Parameters not published.

document(url)PDF/DOCX/PPTX → markdown (no browser, optional `[docs]` extras)

Parameters not published.

extract(url, schema)Scrape + structured extraction (JsonCss schema)

Parameters not published.

health()Versions + import sanity check

Parameters not published.

map_site(root, include_pattern=None, limit=200)Enumerate all internal URLs

Parameters not published.

monitor(url, action, css_selector=None)Change detection with persisted snapshots + unified diff

Parameters not published.

scrape(url, prefer="auto")Single URL → LLM-ready markdown

Parameters not published.

Show all 13 tools
search(query, limit=10)Web search via DuckDuckGo HTML (no API key)

Parameters not published.

search_papers(query, limit=8, source="arxiv", category=None)Academic search via arXiv + Crossref (no API key) — feed `pdf_url` into `document`

Parameters not published.

session(session, action, ...)Persistent browser session (cookies kept) — login walls, multi-step flows, screenshots

Parameters not published.

Ask AI

✦

Ask AI about PyreCrawl

Powered by Claude · Grounded in docs

I know everything about PyreCrawl. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About PyreCrawl

How do I install PyreCrawl?

Run uvx pyrecrawl, then add the server to your MCP client's configuration.

Is PyreCrawl safe to use with an AI agent?

Its trust score is 37 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is PyreCrawl still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.